SciPost Submission Page
Fast Perfekt: Regression-based refinement of fast simulation
by Moritz Wolf, Lars O. Stietz, Patrick L. S. Connor, Peter Schleper, Samuel Bein
Submission summary
| Authors (as registered SciPost users): | Samuel Bein · Moritz Wolf |
| Submission information | |
|---|---|
| Preprint Link: | https://arxiv.org/abs/2410.15992v2 (pdf) |
| Date submitted: | 2024-12-24 16:52 |
| Submitted by: | Bein, Samuel |
| Submitted to: | SciPost Physics Core |
| Ontological classification | |
|---|---|
| Academic field: | Physics |
| Specialties: |
|
| Approaches: | Experimental, Computational |
Abstract
The availability of precise and accurate simulation is a limiting factor for interpreting and forecasting data in many fields of science and engineering. Often, one or more distinct simulation software applications are developed, each with a relative advantage in accuracy or speed. The quality of insights extracted from the data stands to increase if the accuracy of faster, more economical simulation could be improved to parity or near parity with more resource-intensive but accurate simulation. We present Fast Perfekt, a machine-learned regression that employs residual neural networks to refine the output of fast simulations. A deterministic morphing model is trained using a unique schedule that makes use of the ensemble loss function MMD, with the option of an additional pair-based loss function such as the MSE. We explore this methodology in the context of an abstract analytical model and in terms of a realistic particle physics application featuring jet properties in hadron collisions at the CERN Large Hadron Collider. The refinement makes maximum use of domain knowledge, and introduces minimal computational overhead to production.
Author comments upon resubmission
List of changes
Added the sentence in the conclusions: “The refinement acts on final variables or summary statistics of the simulation (i.e., jet properties) rather than intermediate quantities (i.e., calorimeter shower hits).”
Added a qualifying statement: “We also note that the network cannot refine the hidden variable itself, but only correlations to the target hidden variable.”
Modified the sentences to emphasize that the Delphes and modified Delphes are only taken as proxies of fastsim and fullsim, and are not actual fastsim and fullsim: “These events are then processed twice in parallel using Delphes, once with the default CMS detector implementation and treated as the fullsim data set, and once with a ‘flawed’ implementation yielding the data set we treat as the fastsim.”
Moved the definition and citation of MDMM to where it is first introduced (below Equation 4).
Changed “based on” to “tailored to” in the introduction of Section 4 to avoid the impression that real data were used.
Added references for extra ML4Sim context with specific/review-based examples from the literature.